Hyperspectral Image Classification via Cascaded Spatial Cross-Attention Network

Bo Zhang;Yaxiong Chen;Shengwu Xiong;Xiaoqiang Lu
{"title":"Hyperspectral Image Classification via Cascaded Spatial Cross-Attention Network","authors":"Bo Zhang;Yaxiong Chen;Shengwu Xiong;Xiaoqiang Lu","doi":"10.1109/TIP.2025.3533205","DOIUrl":null,"url":null,"abstract":"In hyperspectral images (HSIs), different land cover (LC) classes have distinct reflective characteristics at various wavelengths. Therefore, relying on only a few bands to distinguish all LC classes often leads to information loss, resulting in poor average accuracy. To address this problem, we propose a method called Cascaded Spatial Cross-Attention Network (CSCANet) for HSI classification. We design a cascaded spatial cross-attention module, which first performs cross-attention on local and global features in the spatial context, then uses a group cascade structure to sequentially propagate important spatial regions within the different channels, and finally obtains joint attention features to improve the robustness of the network. Moreover, we also design a two-branch feature separation structure based on spatial-spectral features to separate different LC Tokens as much as possible, thereby improving the distinguishability of different LC classes. Extensive experiments demonstrate that our method achieves excellent performance in enhancing classification accuracy and robustness. The source code can be obtained from <uri>https://github.com/WUTCM-Lab/CSCANet</uri>.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":"34 ","pages":"899-913"},"PeriodicalIF":0.0000,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","FirstCategoryId":"1085","ListUrlMain":"https://ieeexplore.ieee.org/document/10857952/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

In hyperspectral images (HSIs), different land cover (LC) classes have distinct reflective characteristics at various wavelengths. Therefore, relying on only a few bands to distinguish all LC classes often leads to information loss, resulting in poor average accuracy. To address this problem, we propose a method called Cascaded Spatial Cross-Attention Network (CSCANet) for HSI classification. We design a cascaded spatial cross-attention module, which first performs cross-attention on local and global features in the spatial context, then uses a group cascade structure to sequentially propagate important spatial regions within the different channels, and finally obtains joint attention features to improve the robustness of the network. Moreover, we also design a two-branch feature separation structure based on spatial-spectral features to separate different LC Tokens as much as possible, thereby improving the distinguishability of different LC classes. Extensive experiments demonstrate that our method achieves excellent performance in enhancing classification accuracy and robustness. The source code can be obtained from https://github.com/WUTCM-Lab/CSCANet.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
求助全文
约1分钟内获得全文 去求助
相关文献
Ethics and Human–Animal Relations: Review Essay
IF 1.8 4区 哲学Journal of Agricultural & Environmental EthicsPub Date : 2021-07-09 DOI: 10.1007/s10806-021-09864-1
Anna Peterson
Job Crafting and Performance: Literature Review and Implications for Human Resource Development
IF 6.4 3区 管理学Human Resource Development ReviewPub Date : 2018-07-25 DOI: 10.1177/1534484318788269
Jae Young Lee, Yunsoo Lee
Book Review: Editorial Essay: How Workplace Ethnographies Can Inform the Study of Work and Employment Relations
IF 2.8 3区 管理学ILR ReviewPub Date : 2016-02-05 DOI: 10.1177/0019793915621746
Michel Anteby, Beth A. Bechky
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Energy-Adaptive Bitstream-Layer Model for Perceptual Quality Assessment of V-PCC Encoded 3D Point Clouds Commonality Feature Representation Learning for Unsupervised Multimodal Change Detection ADStereo: Efficient Stereo Matching With Adaptive Downsampling and Disparity Alignment Latent Space Learning-Based Ensemble Clustering Contrastive Neuron Pruning for Backdoor Defense
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1